UV-activated conductances allow for multiple time scale learning

Ultraviolet (UV) photoinjection of electrons through SiO(2 ) provides a convenient and simple method for programming analog, nonvolatile memories in CMOS circuits. The time scales involved in the UV programming process are well suited to multiple time scale learning algorithms providing several orders of magnitude in programming rate. The method requires no special processing technology. Measured characteristics of the UV photoinjection devices and experimental results from a synapse circuit built using these devices are presented. This synapse circuit includes a continuously adjustable weight, an electronic learn/hold control and slow forgetting dynamics, while allowing an unimpeded multiplication operation at all times.

[1]  D. Dimaria,et al.  Capture and emission of electrons at 2.4-eV-deep trap level in SiO2films , 1975 .

[2]  S. Tam,et al.  An electrically trainable artificial neural network (ETANN) with 10240 'floating gate' synapses , 1990, International 1989 Joint Conference on Neural Networks.

[3]  R. Tawel,et al.  A CMOS UV-programmable non-volatile synaptic array , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[4]  W. Guggenbuhl,et al.  An analog trimming circuit based on a floating-gate device , 1988 .

[5]  D. Frohman-Bentchkowsky,et al.  Dynamic model of trapping‐detrapping in SiO2 , 1985 .

[6]  E. Vittoz,et al.  Analog Storage of Adjustable Synaptic Weights , 1991 .

[7]  L. Carley,et al.  Trimming analog circuits using floating-gate analog MOS memory , 1989, IEEE International Solid-State Circuits Conference, 1989 ISSCC. Digest of Technical Papers.

[8]  Jin Luo,et al.  CMOS UV-writable non-volatile analog storage , 1991 .

[9]  Fernando J. Pineda,et al.  Dynamics and architecture for neural computation , 1988, J. Complex..